INDEX

Explanations

words and phrases that appear mainly in scientific publications and research papers

Scientific texts

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

Hochspringen

-0.53

 sereia

-0.52

ChildScrollView

-0.52

 nakalista

-0.50

 ouvriers

-0.48

存于互联网档案馆

-0.47

 GenerationType

-0.47

دانشنامهٔ

-0.47

$_[

-0.47

 onAnimation

-0.47

POSITIVE LOGITS

do

1.84

 have

1.42

don

1.20

do

1.16

 make

1.15

are

1.13

Do

1.11

 contribute

1.07

 provide

1.07

Do

1.07

Activations Density 31.966%